Instructions to use Lodo97/coder-2b-v0.1-hfrl with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Lodo97/coder-2b-v0.1-hfrl with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Lodo97/coder-2b-v0.1-hfrl", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Lodo97/coder-2b-v0.1-hfrl", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Lodo97/coder-2b-v0.1-hfrl", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Lodo97/coder-2b-v0.1-hfrl with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Lodo97/coder-2b-v0.1-hfrl"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Lodo97/coder-2b-v0.1-hfrl",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Lodo97/coder-2b-v0.1-hfrl

SGLang

How to use Lodo97/coder-2b-v0.1-hfrl with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Lodo97/coder-2b-v0.1-hfrl" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Lodo97/coder-2b-v0.1-hfrl",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Lodo97/coder-2b-v0.1-hfrl" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Lodo97/coder-2b-v0.1-hfrl",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Lodo97/coder-2b-v0.1-hfrl with Docker Model Runner:
```
docker model run hf.co/Lodo97/coder-2b-v0.1-hfrl
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Card for Model ID

Coder-2b is a phi-2 fine tuned model trained on jondurbin/py-dpo-v0.1 using Reinforcement Learning from Human Feedback with DPO. it is an instruct model capable of generating code starting from an instruction given by the user. It is intended for those people who have few hardware resources available and want to speed up the process of writing Python code.

Model Details

Model Description

with the idea of creating a model that works on limited hardware, starting from a phi-2 model, coder-2b was fine-tuned with the Vezora/Tested-22k-Python-Alpaca dataset to make it capable of creating python code starting from from a user-written prompt. With further fine tuning, using the jondurbin/py-dpo-v0.1 dataset and leveraging the RLHF DPO technique, the model was further improved to produce more accurate outputs.

Developed by: Lodo97
Language(s) (NLP): English
Finetuned from model Lodo97/Test1:

Model Sources [optional]

Repository: Lodo97/coder-2b-v0.1-hfrl
Paper [optional]: [More Information Needed]
Demo [optional]: [More Information Needed]

Uses

Generate python code from an instruction provided by the user
Find errors and bugs
Rewrite code

Direct Use

[More Information Needed]

Downstream Use [optional]

[More Information Needed]

Out-of-Scope Use

[More Information Needed]

Bias, Risks, and Limitations

[More Information Needed]

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

How to Get Started with the Model

Use the code below to get started with the model.

[More Information Needed]

Training Details

Training Data

[More Information Needed]

Training Procedure

Preprocessing [optional]

[More Information Needed]

Training Hyperparameters

Training regime: [More Information Needed]

Speeds, Sizes, Times [optional]

[More Information Needed]

Evaluation

Testing Data, Factors & Metrics

Testing Data

[More Information Needed]

Factors

[More Information Needed]

Metrics

[More Information Needed]

Results

[More Information Needed]

Summary

Model Examination [optional]

[More Information Needed]

Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

Hardware Type: [More Information Needed]
Hours used: [More Information Needed]
Cloud Provider: [More Information Needed]
Compute Region: [More Information Needed]
Carbon Emitted: [More Information Needed]

Technical Specifications [optional]

Model Architecture and Objective

[More Information Needed]

Compute Infrastructure

[More Information Needed]

Hardware

[More Information Needed]

Software

[More Information Needed]

Citation [optional]

BibTeX:

[More Information Needed]

APA:

[More Information Needed]

Glossary [optional]

[More Information Needed]

More Information [optional]

[More Information Needed]

Model Card Authors [optional]

[More Information Needed]

Model Card Contact

[More Information Needed]

Downloads last month: 31

Safetensors

Model size

3B params

Tensor type

F16

Model tree for Lodo97/coder-2b-v0.1-hfrl

Quantizations

2 models

Paper for Lodo97/coder-2b-v0.1-hfrl

Quantifying the Carbon Emissions of Machine Learning

Paper • 1910.09700 • Published Oct 21, 2019 • 45